Success of precision farming practices requires knowledge of fields such as soil type, topography, soil nutrients, spatial variability effects, yield patterns and their spatial relationships. A three year (2008-09 to 2010-11) field experimental study was conducted at Postgraduate Agricultural Research Station, University of Agriculture, Faisalabad, Pakistan, to identify the influencing landscape parameters and their spatial distribution, having effects on wheat yield patterns using artificial neural network (ANN) and GIS map overlay techniques. A total of 48 soil samples were collected from top 30 cm of the soil, before sowing, at center of each grid of 24 x 67 m in size along with position data using Global Positioning System receiver (GARMIN, GPS60). Landscape attributes such as elevation, %sand, %silt, %clay, soil electrical conductivity (EC), pH, soil nitrogen (N) and soil phosphorus were included in the analysis. ANN analysis revealed that urea fertilizer treatments, followed by %sand, %silt, % clay, elevation, soil nitrogen and EC were ranked as the most influencing parameters. The yield data, however, were normalized to remove fertilizer treatments effects and then were used in the subsequent analysis. The map overlay analysis showed that the areas having lower elevation, lower soil EC and higher levels of soil N produced higher yields. Whereas the areas having higher elevation, higher soil EC and moderate soil N produced lower yields, establishing the cause-effect relationships. These results indicated that ANN and GIS techniques were helpful in identifying the influencing parameters affecting wheat yield, which can be managed under precision farming practices.